© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 20302
    Prev
    Next
    INDEX
    Explanations

    verbs related to pride or boasting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    446
    +0.10
    0.5%
    184
    +0.10
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.10
    0.03
    761
    +0.10
    0.04
    59
    +0.09
    0.03
    Negative Logits
    assisted
    -0.63
    through
    -0.59
    zai
    -0.57
    kr
    -0.56
     Reported
    -0.56
     testify
    -0.54
    idian
    -0.54
    bench
    -0.54
     broke
    -0.53
    SOURCE
    -0.53
    POSITIVE LOGITS
     oneself
    1.33
     yourselves
    1.17
     themselves
    1.10
     ourselves
    1.10
     yourself
    1.10
     herself
    1.07
     himself
    1.04
     Yourself
    0.95
     Himself
    0.90
     myself
    0.89
    Activations Density 0.219%

    No Known Activations